🧠
Puro 2b Base model by Thu Pacman
⭐ 39
🧠
Model

Puro 2b Base

by Thu Pacman thu-pacman/puro-2b-base
Free2AITools Nexus Index
39.0
S: Semantic 50

Query-time baseline · scored live at search

A: Authority 0
P: Popularity 18
R: Recency 100
Q: Quality 65
Tech Context
2.03 Params
32.768K Ctx
Vital Performance
388 DL / 30D
Source β†’

Task categories from upstream metadata

πŸ’¬Chat & Dialogue

Technical Constraints

Experimental / High Latency
Low FNI signal 39 FNI Score
Tiny 2.03B Params
32k Context
388 Downloads
8G GPU ~4GB Est. VRAM
Dense QWEN3FORCAUSALLM Architecture
Commercial APACHE License
Model Information Summary
Entity Passport
Registry ID thu-pacman/puro-2b-base
License Apache-2.0
Provider huggingface
πŸ’Ύ

Compute Threshold

~4GB VRAM

Interactive
Estimate fit
β–Ό

* Static estimation for 4-Bit Quantization.

πŸ“œ

Cite this model

Academic & Research Attribution

BibTeX 
@misc{thu_pacman_puro_2b_base,
  author = {Thu Pacman},
  title = {Puro 2b Base Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/thu-pacman/Puro-2B-Base}},
  note = {Accessed via Free2AITools.}
}
APA Style
Thu Pacman. (2026). Puro 2b Base [Model]. Free2AITools. https://huggingface.co/thu-pacman/Puro-2B-Base

πŸ”¬Technical Deep Dive

Full Specifications [+]

Quick Commands

πŸ¦™ Ollama Run
ollama run puro-2b-base
πŸ€— HF Download
huggingface-cli download thu-pacman/puro-2b-base
πŸ“¦ Install Lib
pip install -U transformers

βš–οΈ Free2AITools Nexus Index V2.0

Methodology How FNI works
Semantic (S) 50

Query-time baseline · scored live at search

Authority (A) 0
Popularity (P) 18
Recency (R) 100
Quality (Q) 65

πŸ’¬ Index Insight

FNI V2.0 for Puro 2b Base: Authority (A:0), Popularity (P:18), Recency (R:100), Quality (Q:65). Semantic (S) is a query-time baseline scored live at search.

Free2AITools Nexus Index

Data Sources / Provenance

HuggingFace API GitHub Metadata Arxiv Citation DB Methodology
Open data Updated: Live data
---

πŸš€ What's Next?

πŸ“Š

Models in this category

Browse models in the same category

⚑

Deployment reference

Understand deployment options

Technical Deep Dive

⚠️ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source β†’

πŸ“ Limitations & Considerations

  • β€’ Benchmark scores may vary based on evaluation methodology and hardware configuration.
  • β€’ VRAM requirements are estimates; actual usage depends on quantization and batch size.
  • β€’ FNI scores are relative rankings and may change as new models are added.

Social Proof

HuggingFace Hub
388Downloads
Hub Discussions
πŸ€— Data Source: Hugging Face β†—
πŸ”„ Updated daily

Source summary: Based on Hugging Face metadata. Not a recommendation.

πŸ“Š FNI Methodology πŸ“š Knowledge Baseℹ️ Verify with original source

πŸ›‘οΈ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

πŸ†” Identity & Source

id
hf-model--thu-pacman--puro-2b-base
slug
thu-pacman--puro-2b-base
source
huggingface
author
Thu Pacman
license
Apache-2.0
tags
transformers, safetensors, qwen3, text-generation, base-model, pretraining, fully-open, fp8, rtx-5090, conversational, en, zh, dataset:thu-pacman/puro-2b, license:apache-2.0, text-generation-inference, endpoints_compatible, region:us, arxiv:2608.27370

βš™οΈ Technical Specs

architecture
Qwen3ForCausalLM
params billions
2.03
context length
32,768
pipeline tag
text-generation
vram gb
4
vram is estimated
true
vram formula
VRAM β‰ˆ (params * 0.75) + 2GB (KV) + 0.5GB (OS)

πŸ“Š Engagement & Metrics

downloads
388

Data indexed from public sources. Updated daily.